Install Jentic One Beta

Connect the compresso API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the compresso API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.

Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.

Step 1: Jentic One Host machine

# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fcompresso.space%2Fcompresso" | sh

Step 2: Agent machine

# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fcompresso.space%2Fcompresso" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.

Capabilities

What an agent can do with compresso API.

Compress a PNG, JPEG, or WebP image to a visually lossless, smaller file

Upload an image as a raw body or a multipart form file to compress it

Read today's account usage and verify an API key

Use Cases

Patterns agents use compresso API for, with concrete tasks.

★ Agent-Driven Image Compression

An AI agent connected to the compresso API can compress images as a step in a content pipeline. It posts a PNG, JPEG, or WebP image to the compress endpoint and gets back a visually lossless, smaller file to store or forward, so an agent handling user uploads or generated images can shrink them inline without a separate tool. The usage endpoint lets the agent confirm its key before a batch.

GET STARTED

Start building with compresso API

Explore with Jentic One

View OpenAPI Document

Web Asset Optimization Before Publishing

Large images slow page loads. The compresso API reduces the size of PNG, JPEG, and WebP assets without visible quality loss, so a publishing agent can compress every image in an article before it ships. Because the endpoint returns the optimized image directly, the agent can swap the smaller file straight into the page without a round trip to storage.

Compress each JPEG and PNG referenced in an article and replace them with the smaller returned files

Usage-Aware Batch Compression

When compressing many images, an agent needs to stay within the day's allowance. The compresso API's usage endpoint reports today's account activity, so an agent can check consumption before and during a batch and pause when it nears the limit. The same endpoint doubles as a quick key check at the start of a run.

Read the usage endpoint, then compress a folder of images while stopping if the day's usage nears its limit

Key Endpoints

3 endpoints — the compresso api compresses png, jpeg, and webp images to a visually lossless, smaller file through a single compress endpoint that accepts the image as a raw body or a multipart form upload.

METHOD

PATH

DESCRIPTION

POST

/compress

Compress a PNG, JPEG, or WebP image

GET

/usage

Today's usage for the account and a quick key check

GET

/openapi.json

The OpenAPI document for the API

POST

/compress

Compress a PNG, JPEG, or WebP image

GET

/usage

Today's usage for the account and a quick key check

GET

/openapi.json

The OpenAPI document for the API

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring the compresso API by hand means choosing between its basic-auth and bearer key styles, sending the image with the right content type or as a multipart upload, and handling the 413 and 415 responses. Through Jentic you install once, import compresso from the API Directory, store the key once, and your agent calls it.

Permission scoping

The compresso API carries the image in the request body, not the URL path, so a rule bounds which operations your agent may call rather than which image. You can let it call the compress operation it needs without granting the usage read, and because the surface is small there is little else to expose.

Credential isolation

Your compresso key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.

Intent-based discovery

Agents search Jentic by intent such as 'compress an image' or 'reduce image file size', and Jentic returns the matching compresso operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using compresso API through Jentic.

What authentication does the compresso API use?

The compresso API accepts your API key two ways per its OpenAPI spec: HTTP basic auth, using api as the username and the key as the password (or the key as the username with an empty password), or an Authorization: Bearer header with the key. The spec document endpoint is open. Through Jentic the key is stored once by your own self-hosted instance and injected at call time, so it never sits in your agent's prompt or logs.

Is there a compresso MCP server?

You do not need an MCP server to give your agent the compresso API. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls the compress and usage endpoints on demand. Operations are discovered when needed, so no extra server's tool definitions are loaded into the agent's context.

Can I limit what my agent is allowed to do with the compresso API?

Yes. Write a rule that allows only the compress operation, so the agent can compress images but cannot read your account usage. The compresso API carries the image in the request body, so the rule bounds which operations your agent may call rather than a specific image, and the calls it makes are logged.

What image formats can I compress with the compresso API?

The compress endpoint accepts PNG, JPEG, and WebP images per its OpenAPI spec, sent either as a raw request body with the matching content type or as a multipart form upload with a file field. It returns the compressed image directly, and responds with a 415 when the media type is unsupported and a 413 when the image is too large.

What are the rate limits for the compresso API?

The OpenAPI spec does not state a fixed per-second rate limit, though the compress endpoint can return a 429 when you exceed your allowance. GET /usage reports today's account activity so an agent can pace itself. Check the documentation at https://compresso.space/developers for current plan limits.

How do I compress an image with the compresso API through Jentic?

Search Jentic for 'compress an image' and it returns the POST /compress operation with its input schema. Send a PNG, JPEG, or WebP image and the agent gets back the compressed file. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Compresso Space compresso API

AI ReadinessFoundational (C)57/100

See full scorecard

Official vendor OpenAPI document · agent-readyMediaImage Processingbasic, bearer3 EndpointsREST

For Agents

Compress PNG, JPEG, and WebP images to a visually lossless, smaller file through one compress endpoint, and read today's account usage. Accepts images as a raw body or a multipart form upload.

Use for: Compress a PNG image without visible quality loss, Reduce a JPEG's file size before uploading it, Shrink a WebP image to save bandwidth, Compress an image passed as a multipart form file

Not supported: Does not resize, crop, host, or convert images between formats. Use for visually lossless image compression only.

The compresso API compresses PNG, JPEG, and WebP images to a visually lossless, smaller file through a single compress endpoint that accepts the image as a raw body or a multipart form upload. It returns the optimized image directly, and a usage endpoint reports today's account activity and doubles as a quick key check. The service focuses on size reduction without visible quality loss rather than broader image editing.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A+Signals: 4

99%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

100%

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

75%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: A-Signals: 4

21%

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

67%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: D-Signals: 4

54%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

10%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

94%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: FSignals: 1

35%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: C-Signals: 1

50%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the compresso API to your agent

Capabilities

Use Cases

Start building with compresso API

Key Endpoints

Why Jentic?

Related APIs

FAQs

Compresso Space compresso API

Jentic AI Readiness Score

compresso API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness